Posts in category: Berkeley

We recently built the Berkeley Crossword Solver (BCS), the first computer program to beat every human competitor in the world’s top crossword tournament. The BCS combines neural question answering and probabilistic inference to achieve near-perfect performance on most American-style crossword puzzles, like the one shown below:

Figure 1: Example American-style crossword puzzle

Crosswords are challenging for humans and computers alike. Many clues are vague or underspecified and can’t be answered until crossing constraints are taken into account. While some clues are similar to factoid question answering, others require relational reasoning or understanding difficult wordplay.

We recently published the Berkeley Crossword Solver (BCS), the current state of the art for solving American-style crossword puzzles. The BCS combines neural question answering and probabilistic inference to achieve near-perfect performance on most American-style crossword puzzles, like the one shown below:

Figure 1: Example American-style crossword puzzle

An earlier version of the BCS, in conjunction with Dr.Fill, was the first computer program to outscore all human competitors in the world’s top crossword tournament. The most recent version is the current top-performing system on crossword puzzles from The New York Times, achieving 99.7% letter accuracy (see the technical paper, web demo, and code release).

Figure 1: In real-world applications, we think there exist a human-machine loop where humans and machines are mutually augmenting each other. We call it Artificial Augmented Intelligence.

How do we build and evaluate an AI system for real-world applications? In most AI research, the evaluation of AI methods involves a training-validation-testing process. The experiments usually stop when the models have good testing performance on the reported datasets because real-world data distribution is assumed to be modeled by the validation and testing data. However, real-world applications are usually more complicated than a single training-validation-testing process. The biggest difference is the ever-changing data. For example, wildlife datasets change in class composition all the time because of animal invasion, re-introduction, re-colonization, and seasonal animal movements. A model trained, validated, and tested on existing datasets can easily be broken when newly collected data contain novel species. Fortunately, we have out-of-distribution detection methods that can help us detect samples of novel species. However, when we want to expand the recognition capacity (i.e., being able to recognize novel species in the future), the best we can do is fine-tuning the models with new ground-truthed annotations. In other words, we need to incorporate human effort/annotations regardless of how the models perform on previous testing sets.

Figure 1: In real-world applications, we think there exist a human-machine loop where humans and machines are mutually augmenting each other. We call it Artificial Augmented Intelligence.

How do we build and evaluate an AI system for real-world applications? In most AI research, the evaluation of AI methods involves a training-validation-testing process. The experiments usually stop when the models have good testing performance on the reported datasets because real-world data distribution is assumed to be modeled by the validation and testing data. However, real-world applications are usually more complicated than a single training-validation-testing process. The biggest difference is the ever-changing data. For example, wildlife datasets change in class composition all the time because of animal invasion, re-introduction, re-colonization, and seasonal animal movements. A model trained, validated, and tested on existing datasets can easily be broken when newly collected data contain novel species. Fortunately, we have out-of-distribution detection methods that can help us detect samples of novel species. However, when we want to expand the recognition capacity (i.e., being able to recognize novel species in the future), the best we can do is fine-tuning the models with new ground-truthed annotations. In other words, we need to incorporate human effort/annotations regardless of how the models perform on previous testing sets.

Deep reinforcement learning (DRL) is transitioning from a research field focused on game playing to a technology with real-world applications. Notable examples include DeepMind’s work on controlling a nuclear reactor or on improving Youtube video compression, or Tesla attempting to use a method inspired by MuZero for autonomous vehicle behavior planning. But the exciting potential for real world applications of RL should also come with a healthy dose of caution – for example RL policies are well known to be vulnerable to exploitation, and methods for safe and robust policy development are an active area of research.

At the same time as the emergence of powerful RL systems in the real world, the public and researchers are expressing an increased appetite for fair, aligned, and safe machine learning systems. The focus of these research efforts to date has been to account for shortcomings of datasets or supervised learning practices that can harm individuals. However the unique ability of RL systems to leverage temporal feedback in learning complicates the types of risks and safety concerns that can arise.

This post expands on our recent whitepaper and research paper, where we aim to illustrate the different modalities harms can take when augmented with the temporal axis of RL. To combat these novel societal risks, we also propose a new kind of documentation for dynamic Machine Learning systems which aims to assess and monitor these risks both before and after deployment.

Deep reinforcement learning (DRL) is transitioning from a research field focused on game playing to a technology with real-world applications. Notable examples include DeepMind’s work on controlling a nuclear reactor or on improving Youtube video compression, or Tesla attempting to use a method inspired by MuZero for autonomous vehicle behavior planning. But the exciting potential for real world applications of RL should also come with a healthy dose of caution – for example RL policies are well known to be vulnerable to exploitation, and methods for safe and robust policy development are an active area of research.

At the same time as the emergence of powerful RL systems in the real world, the public and researchers are expressing an increased appetite for fair, aligned, and safe machine learning systems. The focus of these research efforts to date has been to account for shortcomings of datasets or supervised learning practices that can harm individuals. However the unique ability of RL systems to leverage temporal feedback in learning complicates the types of risks and safety concerns that can arise.

This post expands on our recent whitepaper and research paper, where we aim to illustrate the different modalities harms can take when augmented with the temporal axis of RL. To combat these novel societal risks, we also propose a new kind of documentation for dynamic Machine Learning systems which aims to assess and monitor these risks both before and after deployment.

Figure 1: Summary of our recommendations for when a practitioner should BC and various imitation learning style methods, and when they should use offline RL approaches.

Offline reinforcement learning allows learning policies from previously collected data, which has profound implications for applying RL in domains where running trial-and-error learning is impractical or dangerous, such as safety-critical settings like autonomous driving or medical treatment planning. In such scenarios, online exploration is simply too risky, but offline RL methods can learn effective policies from logged data collected by humans or heuristically designed controllers. Prior learning-based control methods have also approached learning from existing data as imitation learning: if the data is generally “good enough,” simply copying the behavior in the data can lead to good results, and if it’s not good enough, then filtering or reweighting the data and then copying can work well. Several recent works suggest that this is a viable alternative to modern offline RL methods.

This brings about several questions: when should we use offline RL? Are there fundamental limitations to methods that rely on some form of imitation (BC, conditional BC, filtered BC) that offline RL addresses? While it might be clear that offline RL should enjoy a large advantage over imitation learning when learning from diverse datasets that contain a lot of suboptimal behavior, we will also discuss how even cases that might seem BC-friendly can still allow offline RL to attain significantly better results. Our goal is to help explain when and why you should use each method and provide guidance to practitioners on the benefits of each approach. Figure 1 concisely summarizes our findings and we will discuss each component.

Figure 1: Summary of our recommendations for when a practitioner should BC and various imitation learning style methods, and when they should use offline RL approaches.

Offline reinforcement learning allows learning policies from previously collected data, which has profound implications for applying RL in domains where running trial-and-error learning is impractical or dangerous, such as safety-critical settings like autonomous driving or medical treatment planning. In such scenarios, online exploration is simply too risky, but offline RL methods can learn effective policies from logged data collected by humans or heuristically designed controllers. Prior learning-based control methods have also approached learning from existing data as imitation learning: if the data is generally “good enough,” simply copying the behavior in the data can lead to good results, and if it’s not good enough, then filtering or reweighting the data and then copying can work well. Several recent works suggest that this is a viable alternative to modern offline RL methods.

This brings about several questions: when should we use offline RL? Are there fundamental limitations to methods that rely on some form of imitation (BC, conditional BC, filtered BC) that offline RL addresses? While it might be clear that offline RL should enjoy a large advantage over imitation learning when learning from diverse datasets that contain a lot of suboptimal behavior, we will also discuss how even cases that might seem BC-friendly can still allow offline RL to attain significantly better results. Our goal is to help explain when and why you should use each method and provide guidance to practitioners on the benefits of each approach. Figure 1 concisely summarizes our findings and we will discuss each component.

A demonstration of the RvS policy we learn with just supervised learning and a depth-two MLP. It uses no TD learning, advantage reweighting, or Transformers!

Offline reinforcement learning (RL) is conventionally approached using value-based methods based on temporal difference (TD) learning. However, many recent algorithms reframe RL as a supervised learning problem. These algorithms learn conditional policies by conditioning on goal states (Lynch et al., 2019; Ghosh et al., 2021), reward-to-go (Kumar et al., 2019; Chen et al., 2021), or language descriptions of the task (Lynch and Sermanet, 2021).

We find the simplicity of these methods quite appealing. If supervised learning is enough to solve RL problems, then offline RL could become widely accessible and (relatively) easy to implement. Whereas TD learning must delicately balance an actor policy with an ensemble of critics, these supervised learning methods train just one (conditional) policy, and nothing else!

A demonstration of the RvS policy we learn with just supervised learning and a depth-two MLP. It uses no TD learning, advantage reweighting, or Transformers!

Offline reinforcement learning (RL) is conventionally approached using value-based methods based on temporal difference (TD) learning. However, many recent algorithms reframe RL as a supervised learning problem. These algorithms learn conditional policies by conditioning on goal states (Lynch et al., 2019; Ghosh et al., 2021), reward-to-go (Kumar et al., 2019; Chen et al., 2021), or language descriptions of the task (Lynch and Sermanet, 2021).

We find the simplicity of these methods quite appealing. If supervised learning is enough to solve RL problems, then offline RL could become widely accessible and (relatively) easy to implement. Whereas TD learning must delicately balance an actor policy with an ensemble of critics, these supervised learning methods train just one (conditional) policy, and nothing else!